# PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation

arXiv: https://arxiv.org/abs/2503.01303 · HTML: https://mlsanity.com/paper/2503.01303/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Mixture of LoRA experts, one of 12 directions in Mixture-of-experts.
- First posted on arXiv 3 Mar 2025.

## Placed in

- Mixture-of-experts / [Mixture of LoRA experts](https://mlsanity.com/moe/mixture-of-lora-experts/)

## Built on by (most cited first, 24 of 24)

- [Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation](https://mlsanity.com/paper/2512.06690/) (2025)
- [Instant Personalized Large Language Model Adaptation via Hypernetwork](https://mlsanity.com/paper/2510.16282/) (2025)
- [Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision](https://mlsanity.com/paper/2505.12532/) (2025)
- [SteerX: Disentangled Steering for LLM Personalization](https://mlsanity.com/paper/2510.22256/) (2025)
- [PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions](https://mlsanity.com/paper/2509.07370/) (2025)
- [Your Language Model Secretly Contains Personality Subnetworks](https://mlsanity.com/paper/2602.07164/) (2026)
- [SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation](https://mlsanity.com/paper/2601.09974/) (2026)
- [CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs](https://mlsanity.com/paper/2602.00742/) (2026)
- [Synthetic Interaction Data for Scalable Personalization in Large Language Models](https://mlsanity.com/paper/2602.12394/) (2026)
- [CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation](https://mlsanity.com/paper/2601.06352/) (2026)
- [When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs](https://mlsanity.com/paper/2601.11000/) (2026)
- [Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization](https://mlsanity.com/paper/2606.04547/) (2026)
- [Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization](https://mlsanity.com/paper/2604.11259/) (2026)
- [PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation](https://mlsanity.com/paper/2601.06471/) (2026)
- [Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization](https://mlsanity.com/paper/2606.02300/) (2026)
- [Self-supervised User Profile Generation for Personalization](https://mlsanity.com/paper/2606.05336/) (2026)
- [Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization](https://mlsanity.com/paper/2608.12389/) (2026)
- [Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures](https://mlsanity.com/paper/2605.10991/) (2026)
- [Evaluating the Hidden Costs of Personalization in Large Language Models](https://mlsanity.com/paper/2608.28833/) (2026)
- [Alignment by Stereotyping: How LLMs Sacrifice Individual Distinctiveness for Cultural Adaptation](https://mlsanity.com/paper/2609.05993/) (2026)
- [HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization](https://mlsanity.com/paper/2609.09835/) (2026)
- [Unlocking Latent Personalization in LLMs](https://mlsanity.com/paper/2609.33182/) (2026)
- [Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation](https://mlsanity.com/paper/2610.02353/) (2026)
- [PersonaFactor: Preference Factors with Dynamic Selection for LLM Personalization](https://mlsanity.com/paper/2610.16372/) (2026)

## Abstract (arXiv)

Personalized large language models (LLMs) aim to tailor their outputs to user preferences. Recent advances in parameter-efficient fine-tuning (PEFT) methods have highlighted the effectiveness of adapting population-level LLMs to personalized LLMs by fine-tuning user-specific parameters with user history. However, user data is typically sparse, making it challenging to adapt LLMs to specific user patterns. To address this challenge, we propose PROgressive PERsonalization (PROPER), a novel progressive learning framework inspired by meso-level theory in social science. PROPER bridges population-level and user-level models by grouping users based on preferences and adapting LLMs in stages. It combines a Mixture-of-Experts (MoE) structure with Low Ranked Adaptation (LoRA), using a user-aware router to assign users to appropriate groups automatically. Additionally, a LoRA-aware router is proposed to facilitate the integration of individual user LoRAs with group-level LoRAs. Experimental results show that PROPER significantly outperforms SOTA models across multiple tasks, demonstrating the effectiveness of our approach.